Turing Pi
@turingpi

From homelab and edge AI to local LLMs, Turing Pi handles it all. Datacenter-level compute in a desktop design. Join the community discord.gg/uNbysyc

 United States
turingpi.com
Joined June 2019
413 Photos and videos
Article

Jetson vs Microcontroller: When Robots Need Both

A Jetson Orin Nano can run object detection, speech recognition, and a ROS 2 navigation stack. With the right pins exposed on its carrier, it can also send PWM signals to a motor driver. If you

2
1
18
2,963
ngmi if your cluster isn't sitting on your desk.
1
26
2,052
Friday build check. Show us your cluster. Rack, shelf or shoebox, all count.
1
27
1,650
Article

ARM64 Docker Compatibility: 32 Images Checked (2026)

ARM64 Docker compatibility matters when you move the applications you rely on to a new server. A web interface may load while a background worker fails, a database extension is unavailable, or

1
1
14
1,742
The best place to learn Kubernetes is a cluster you're allowed to break.
1
26
1,384
One board. Four slots. Pick a chip for each job. >RK1 for k3s and databases >Jetson Orin NX for vision and local LLMs >CM4 for the small stuff that just has to stay up Mix them in any combination on a Turing Pi 2.5. What goes in your four slots?
10
1,431
Article

Whisper vs Parakeet on Jetson Orin Nano: Benchmarks

A speech-to-text model might recognize clean recordings perfectly and still be the wrong choice for an 8GB Jetson Orin Nano. Conversational speech is harder, processing speed varies widely, and the

1
1
13
1,397
Private by default. No settings page required.
1
22
1,532
NVIDIA's new Nemotron model is the brain of this robot, running on a Jetson Orin Nano 8GB. The model needs only 4.2 GB of memory and does 15.5 tokens a second. On a Turing Pi 2.5, that's just one slot.
1
22
1,958
NVIDIA's numbers for Nemotron 3.5 Bolt E4B (Q4_K_M, llama.cpp, 3K prompt): research.nvidia.com/labs/nem…

NVIDIA Nemotron 3.5 Bolt E4B 4GB

We are releasing NVIDIA Nemotron 3.5 Bolt E4B 4GB, an open small language model optimized for speed and intelligence per GB in conversational agents.

research.nvidia.com
7
513
Article

YOLO on Jetson Orin Nano: FPS, Latency and TensorRT Benchmarks

YOLO11n ran 1.83× faster in serial replay with TensorRT than with PyTorch FP32 on our Jetson Orin Nano 8GB. In live runs receiving about 20 camera frames per second, TensorRT recorded a median per-run

1
10
1,201
Things your homelab will never do: >raise the price >deprecate your plan >sunset the feature you rely on >update the terms of service >show you ads Buy it once. It's yours.
6
25
1,411
If you self-host Nextcloud, WordPress or anything else on PHP, update tonight. Two flaws let attackers run code on your server without logging in. Attacks have already started. Fixed in PHP 8.5.12, 8.4.27, 8.3.36 and 8.2.35. There's no workaround.
3
17
1,902
Things that shouldn't live in someone else's cloud: >your camera footage >your voice commands >your family photos >your passwords 4 nodes. One board. Your house.
2
2
37
1,900
For anyone asking what's in the photo: turingpi.com/product/turing-…

Get Turing Pi 2, mini ITX cluster board

The Turing Pi 2.5 is a 4-node mini ITX cluster board with a built-in Ethernet switch that runs Turing RK1, Raspberry Pi CM4 or Nvidia Jetson compute modules

turingpi.com
2
398
Article

How Voice Assistants Work and Why They Feel Slow

You ask a voice assistant to turn off the kitchen lights. It hears the words correctly, pauses, then answers. You start correcting it halfway through the reply, but it keeps talking. The speech
17
1,545
Your security camera shouldn't come with a subscription to your own footage. Run AI-powered object detection locally on a Jetson module inside Turing Pi 2.5. No cloud required for detection. No monthly AI inference fees. Just your cameras, your hardware, and your data. And that's only one of four compute slots.
1
2
55
2,143
Article

Frigate on Jetson Orin Nano: Camera Tests on Turing Pi 2.5

We tested Frigate on a Jetson Orin Nano Super installed in Turing Pi 2.5, using a USB webcam and NVMe storage to capture video, detect people and record events locally. Then we measured the camera
1
15
1,493
Anthropic ran a 26B model on 15 cheap TV boxes >paper: "AI models may be capable of self-replicating without access to a datacenter" >15 off-brand Android TV boxes, about $55 each >4GB of RAM per box >Gemma4-26B split by layers across all 15 >it worked >0.39 tokens per second >why so slow? only one box works at a time >the other 14 wait Homelab lesson: splitting a model across weak nodes doesn't add up their speed. Fit it in one node's memory and use the rest of the cluster for everything else. anthropic.com/research/self-…

AI models may be capable of self-replicating without access to a datacenter

Small AI models may be only months away from being able to self-replicate across cheap IoT devices like Android TV boxes, with no datacenter needed.

anthropic.com
1
1
18
1,672
Paying $15/month to host an app? Another $15 for your database? Another $15 for a side project? Those subscriptions add up. With Turing Pi 2.5, you can run up to 4 compute nodes on one board. Host your apps, databases, containers, and local AI workloads on hardware you control. No per-app cloud hosting bills for what you self-host. Just your hardware, power, and internet. Stop renting compute. Start owning it. Build your own cluster → turingpi.com
17
1,281
Load more